mums the word on Flash?

I would love to know what the increased token count is across these models for the benchmarks. I find the models continue to get better but as they do their token usage also does. Aka is model doing better or reasoning for longer?

I think that is always something that is being worked on in parallel. Recent paradigm seems to be the models understanding when they need to use more tokens dynamically (which seems to be very much in line with how computation should generally work).

It's pretty wild that Brave's terms of service state as much, considering their search API is entirely derived from storing the results of other search systems. https://support.brave.app/hc/en-us/articles/4409406835469-Wh.... Aka Brave is blocking exactly what it does to Bing and Google.

I think you would be very surprised by the number of customers who don't care if the embeddings are SOTA. For every Joe who wants to talk GraphRAG + MTEB + CMTEB and adaptive rag there are 50 who just want whatever IT/prodsec has approved

they also 10xed their revenue. 24 seems low for someone that pulled that off.

GPT-4o as a judge to evaluate the quality of something which gpt4o is not inherently that good at. Red flag.

does it do the full 100? In my experience anything around many items that needs to be exhaustive (all states, all fortune 100) tends to miss a few.

It's not free because it's cheap for them to run. It's free because they are burning that late-stage VC dollars. Despite what you might believe if you only follow them on twitter the biggest input to their product, aka a search index, is mostly based on brave/bing/serpAPI and those numbers are pretty tight. Big expectations for ads will determine what the company does.

This works better because it gives a secondary set of conditions for which the decoder (generating text) is conditioning its generation. Assume instead of their demo you are doing Speech2Text for Oncologists. Out of the Box Whisper is terrible because the words are new and rare, especially in YouTube videos. If you just run ASR through it and run NER, it will generate regular words over cancer names. Instead, if you condition generation on topical entities the generation space is constrained and performance will improve. Especially when you can tell the model what all the drug names are because you have a list (https://www.cancerresearchuk.org/about-cancer/treatment/drug...)

https://www.youtube.com/watch?v=ecnS1Ygf0o0 I've been waiting for the chance to use this